Individual skill

reproduce

End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a paper from scratch, or pastes an arxiv URL with reproduction intent.

plugin/skills/reproduce/SKILL.md

Read pinned source

Source commit 04877622ff124d92d9ee8377109499c0afc6bf01

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 455
Repository last updated: Nov 1, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

academic Repository topic
claude-code Repository topic
phd Repository topic
research Repository topic
agents Repository topic
ai Repository topic
claude Repository topic
hooks Repository topic
mcp Repository topic
plugin Repository topic
research Derived category
testing Derived category
testing-browser Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,532 bytes
references/01-paper-fetch.mddoc · 3,883 bytes
references/02-code-clone.mddoc · 4,089 bytes
references/03-gap-analysis.mddoc · 5,674 bytes
references/04-implement.mddoc · 4,399 bytes
references/05-dataset.mddoc · 4,672 bytes
references/06-smoke.mddoc · 4,687 bytes
references/07-replicate.mddoc · 4,956 bytes

Read excerpt


# Reproduce: paper reproduction from scratch

Reproducing an ML paper often means filling gaps the authors didn't ship, training scripts, hyperparameter tables, augmentation specifics, exact dataset splits. This skill walks seven stages from "I have an arxiv link" to "I have a replication run with measurable delta vs the paper's number."

Each stage has a separate reference file under `references/` so this overview stays scannable.

## When to run

The user just said any of:

- "reproduce / implement / replicate / re-run paper X"
- pasted an arxiv URL with reproduction intent ("can you redo this", "let's try this approach")
- pointed at an OpenReview / proceedings link with the same intent
- said "the paper has no code, can we build it"